INDEX

Explanations

references to official documents or web resources

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hunts

-0.16

 tape

-0.14

deg

-0.14

odal

-0.14

ó

-0.13

 absentee

-0.13

hausen

-0.13

æĵį

-0.13

animate

-0.13

ÐºÐ¾

-0.13

POSITIVE LOGITS

actionDate

0.20

istrovstvÃŃ

0.16

Regs

0.15

ãĥ¼ãĥĸãĥ«

0.14

OffsetTable

0.14

à¥ĭà¥ľ

0.14

æŀĿ

0.14

GuidId

0.14

Rat

0.14

ignet

0.13

Activations Density 0.016%

references to official documents or web resources

No Comments

No Known Activations